Module:languages/data2
Documentation for this module may be created at Module:languages/data2/doc
local u = mw.ustring.char
-- Private use characters for sortkey placement.
local a, b, c, d, e, f, g, h = u(0xF000), u(0xF001), u(0xF002), u(0xF003), u(0xF004), u(0xF005), u(0xF006), u(0xF007)
-- UTF-8 encoded strings for some commonly-used diacritics
local GRAVE = u(0x300)
local ACUTE = u(0x301)
local CIRC = u(0x302)
local TILDE = u(0x303)
local MACRON = u(0x304)
local BREVE = u(0x306)
local DOTABOVE = u(0x307)
local DIAER = u(0x308)
local RINGABOVE = u(0x30A)
local DACUTE = u(0x30B)
local CARON = u(0x30C)
local DGRAVE = u(0x30F)
local INVBREVE = u(0x311)
local DOTBELOW = u(0x323)
local DIAERBELOW = u(0x324)
local RINGBELOW = u(0x325)
local CEDILLA = u(0x327)
local OGONEK = u(0x328)
local BREVEBELOW = u(0x32E)
local CGJ = u(0x34F) -- combining grapheme joiner
local DOUBLEINVBREVE = u(0x361)
local KASHIDA = u(0x640)
local FATHATAN = u(0x64B)
local DAMMATAN = u(0x64C)
local KASRATAN = u(0x64D)
local FATHA = u(0x64E)
local DAMMA = u(0x64F)
local KASRA = u(0x650)
local SHADDA = u(0x651)
local SUKUN = u(0x652)
local NUNGHUNNA = u(0x658)
local SUPERALEF = u(0x670)
-- Punctuation to be used for standardChars field
local PUNCTUATION = ' !#%&*+,-./:;<=>?@^_`|~\'()∅'
-- Use these in "scripts" to save a little memory.
local Arab = {"Arab"}
local CansLatn = {"Cans", "Latn"}
local Cyrl = {"Cyrl"}
local CyrlGeorLatn = {"Cyrl", "Geor", "Latn"}
local CyrlLatnArab = {"Cyrl", "Latn", "Arab"}
local Deva = {"Deva"}
local Ethi = {"Ethi"}
local Latn = {"Latn"}
local LatnArab = {"Latn", "Arab"}
local LatnBrai = {"Latn", "Brai"}
local LatnCyrlfaArab = {"Latn", "Cyrl", "fa-Arab"}
local LatnHani = {"Latn", "Hani"}
local LatnLatg = {"Latn", "Latg"}
local Tibt = {"Tibt"}
local m = {}
m["aa"] = {
"Afar",
27811,
"cus-eas",
Latn,
entry_name = {remove_diacritics = ACUTE},
}
m["ab"] = {
"Abkhaz",
5111,
"cau-abz",
CyrlGeorLatn,
translit_module = "translit-redirect",
override_translit = true,
display_text = {Cyrl = "cau-Cyrl-displaytext"},
entry_name = {
Cyrl = "cau-Cyrl-entryname",
Latn = "cau-Latn-entryname",
},
sort_key = {
Cyrl = {
from = {
"х'ә", -- 3 chars
"гь", "гә", "ӷь", "ҕь", "ӷә", "ҕә", "дә", "ё", "жь", "жә", "ҙә", "ӡә", "ӡ'", "кь", "кә", "қь", "қә", "ҟь", "ҟә", "ҫә", "тә", "ҭә", "ф'", "хь", "хә", "х'", "ҳә", "ць", "цә", "ц'", "ҵә", "ҵ'", "шь", "шә", "џь", -- 2 chars
"ӷ", "ҕ", "ҙ", "ӡ", "қ", "ҟ", "ԥ", "ҧ", "ҫ", "ҭ", "ҳ", "ҵ", "ҷ", "ҽ", "ҿ", "ҩ", "џ", "ә" -- 1 char
},
to = {
"х" .. d,
"г" .. a, "г" .. b, "г" .. e, "г" .. f, "г" .. g, "г" .. h, "д" .. a, "е" .. a, "ж" .. a, "ж" .. b, "з" .. b, "з" .. d, "з" .. e, "к" .. a, "к" .. b, "к" .. d, "к" .. e, "к" .. g, "к" .. h, "с" .. b, "т" .. a, "т" .. c, "ф" .. a, "х" .. a, "х" .. b, "х" .. c, "х" .. f, "ц" .. a, "ц" .. b, "ц" .. c, "ц" .. e, "ц" .. f, "ш" .. a, "ш" .. b, "ы" .. c,
"г" .. c, "г" .. d, "з" .. a, "з" .. c, "к" .. c, "к" .. f, "п" .. a, "п" .. b, "с" .. a, "т" .. b, "х" .. e, "ц" .. d, "ч" .. a, "ч" .. b, "ч" .. c, "ы" .. a, "ы" .. b, "ь" .. a
}
},
},
}
m["ae"] = {
"Avestan",
29572,
"ira-cen",
{"Avst", "Gujr"},
translit_module = "Avst-translit",
wikipedia_article = "Avestan",
}
m["af"] = {
"Afrikaans",
14196,
"gmw",
LatnArab,
ancestors = {"nl"},
sort_key = {
Latn = {
remove_diacritics = GRAVE .. ACUTE .. CIRC .. TILDE .. DIAER .. RINGABOVE .. CEDILLA .. "'",
from = {"['ʼ]n"},
to = {"n" .. a}
}
},
}
m["ak"] = {
"Akan",
28026,
"alv-ctn",
Latn,
}
m["am"] = {
"Amharic",
28244,
"sem-eth",
Ethi,
translit_module = "Ethi-translit",
}
m["an"] = {
"Aragonese",
8765,
"roa-ibe",
Latn,
ancestors = {"roa-oan"},
}
m["ar"] = {
"Arabic",
13955,
"sem-arb",
{"Arab", "Hebr", "Brai"},
translit_module = "ar-translit",
entry_name = {Arab = "ar-entryname"},
-- put Judeo-Arabic (Hebrew-script Arabic) under the category header
-- U+FB21 HEBREW LETTER WIDE ALEF so that it sorts after Arabic script titles
sort_key = {
Arab = {
from = {"^%f[" .. u(0x5D0) .. "-" .. u(0x5EA) .. "]"},
to = {u(0xFB21)},
},
},
}
m["as"] = {
"Assamese",
29401,
"inc-eas",
{"as-Beng"},
ancestors = {"inc-mas"},
translit_module = "as-translit",
}
m["av"] = {
"Avar",
29561,
"cau-ava",
CyrlLatnArab,
ancestors = {"oav"},
translit_module = "translit-redirect",
override_translit = true,
display_text = {Cyrl = "cau-Cyrl-displaytext"},
entry_name = {
Cyrl = "cau-Cyrl-entryname",
Latn = "cau-Latn-entryname",
},
sort_key = {
Cyrl = {
from = {"гъ", "гь", "гӏ", "ё", "кк", "къ", "кь", "кӏ", "лъ", "лӏ", "тӏ", "хх", "хъ", "хь", "хӏ", "цӏ", "чӏ"},
to = {"г" .. a, "г" .. b, "г" .. c, "е" .. a, "к" .. a, "к" .. b, "к" .. c, "к" .. d, "л" .. a, "л" .. b, "т" .. a, "х" .. a, "х" .. b, "х" .. c, "х" .. d, "ц" .. a, "ч" .. a}
},
},
}
m["ay"] = {
"Aymara",
4627,
"sai-aym",
Latn,
}
m["az"] = {
"Azerbaijani",
9292,
"trk-ogz",
LatnCyrlfaArab,
ancestors = {"trk-oat"},
dotted_dotless_i = true,
entry_name = {remove_diacritics = KASHIDA .. FATHATAN .. DAMMATAN .. KASRATAN .. FATHA .. DAMMA .. KASRA .. SHADDA .. SUKUN},
sort_key = {
Latn = {
from = {
"i", -- Ensure "i" comes after "ı".
"ç", "ə", "ğ", "x", "ı", "q", "ö", "ş", "ü", "w"
},
to = {
"i" .. a,
"c" .. a, "e" .. a, "g" .. a, "h" .. a, "i", "k" .. a, "o" .. a, "s" .. a, "u" .. a, "z" .. a
}
},
Cyrl = {
from = {"ғ", "ә", "ы", "ј", "ҝ", "ө", "ү", "һ", "ҹ"},
to = {"г" .. a, "е" .. a, "и" .. a, "и" .. b, "к" .. a, "о" .. a, "у" .. a, "х" .. a, "ч" .. a}
},
},
}
m["ba"] = {
"Bashkir",
13389,
"trk-kbu",
Cyrl,
translit_module = "ba-translit",
override_translit = true,
sort_key = {
from = {"ғ", "ҙ", "ё", "ҡ", "ң", "ө", "ҫ", "ү", "һ", "ә"},
to = {"г" .. a, "д" .. a, "е" .. a, "к" .. a, "н" .. a, "о" .. a, "с" .. a, "у" .. a, "х" .. a, "э" .. a}
},
}
m["be"] = {
"Belarusian",
9091,
"zle",
Cyrl,
ancestors = {"zle-ort"},
translit_module = "be-translit",
entry_name = {remove_diacritics = GRAVE .. ACUTE},
sort_key = {
from = {"ґ", "ё", "і", "ў"},
to = {"г" .. a, "е" .. a, "и" .. a, "у" .. a}
},
}
m["bg"] = {
"Bulgarian",
7918,
"zls",
Cyrl,
ancestors = {"cu"},
translit_module = "bg-translit",
entry_name = {remove_diacritics = GRAVE .. ACUTE},
}
m["bh"] = {
"Bihari",
135305,
"inc-eas",
Deva,
ancestors = {"inc-mgd"},
}
m["bi"] = {
"Bislama",
35452,
"crp",
Latn,
ancestors = {"en"},
}
m["bm"] = {
"Bambara",
33243,
"dmn-emn",
Latn,
sort_key = {
from = {"ɛ", "ɲ", "ŋ", "ɔ"},
to = {"e" .. a, "n" .. a, "n" .. b, "o" .. a}
},
}
m["bn"] = {
"Bengali",
9610,
"inc-eas",
{"Beng", "Newa"},
ancestors = {"inc-mbn"},
translit_module = "bn-translit",
}
m["bo"] = {
"Tibetan",
34271,
"sit-tib",
Tibt, -- sometimes Deva?
ancestors = {"xct"},
translit_module = "Tibt-translit",
override_translit = true,
display_text = "Tibt-displaytext",
entry_name = "Tibt-entryname",
sort_key = "Tibt-sortkey",
}
m["br"] = {
"Breton",
12107,
"cel-bry",
Latn,
ancestors = {"xbm"},
sort_key = {
from = {"ch", "c['ʼ’]h"},
to = {"c" .. a, "c" .. b}
},
}
m["ca"] = {
"Catalan",
7026,
"roa-ocr",
Latn,
ancestors = {"roa-oca"},
sort_key = {
remove_diacritics = GRAVE .. ACUTE .. DIAER .. CEDILLA,
from = {"l·l"},
to = {"ll"}
},
}
m["ce"] = {
"Chechen",
33350,
"cau-vay",
CyrlLatnArab,
translit_module = "translit-redirect",
override_translit = true,
display_text = {Cyrl = "cau-Cyrl-displaytext"},
entry_name = {
Cyrl = "cau-Cyrl-entryname",
Latn = "cau-Latn-entryname",
},
sort_key = {
Cyrl = {
from = {"аь", "гӏ", "ё", "кх", "къ", "кӏ", "оь", "пӏ", "тӏ", "уь", "хь", "хӏ", "цӏ", "чӏ", "юь", "яь"},
to = {"а" .. a, "г" .. a, "е" .. a, "к" .. a, "к" .. b, "к" .. c, "о" .. a, "п" .. a, "т" .. a, "у" .. a, "х" .. a, "х" .. b, "ц" .. a, "ч" .. a, "ю" .. a, "я" .. a}
},
},
}
m["ch"] = {
"Chamorro",
33262,
"poz-sus",
Latn,
sort_key = {
remove_diacritics = "'",
from = {"å", "ch", "ñ", "ng"},
to = {"a" .. a, "c" .. a, "n" .. a, "n" .. b}
},
}
m["co"] = {
"Corsican",
33111,
"roa-itd",
Latn,
sort_key = {
from = {"chj", "ghj", "sc", "sg"},
to = {"c" .. a, "g" .. a, "s" .. a, "s" .. b}
},
}
m["cr"] = {
"Cree",
33390,
"alg",
CansLatn,
translit_module = "translit-redirect",
}
m["cs"] = {
"Czech",
9056,
"zlw",
Latn,
ancestors = {"zlw-ocs"},
sort_key = {
from = {"á", "č", "ď", "é", "ě", "ch", "í", "ň", "ó", "ř", "š", "ť", "ú", "ů", "ý", "ž"},
to = {"a" .. a, "c" .. a, "d" .. a, "e" .. a, "e" .. b, "h" .. a, "i" .. a, "n" .. a, "o" .. a, "r" .. a, "s" .. a, "t" .. a, "u" .. a, "u" .. b, "y" .. a, "z" .. a}
},
}
m["cu"] = {
"Old Church Slavonic",
35499,
"zls",
{"Cyrs", "Glag"},
translit_module = "Cyrs-Glag-translit",
entry_name = {Cyrs = "Cyrs-entryname"},
sort_key = {Cyrs = "Cyrs-sortkey"},
}
m["cv"] = {
"Chuvash",
33348,
"trk-ogr",
Cyrl,
ancestors = {"xbo"},
translit_module = "cv-translit",
override_translit = true,
sort_key = {
from = {"ӑ", "ё", "ӗ", "ҫ", "ӳ"},
to = {"а" .. a, "е" .. a, "е" .. b, "с" .. a, "у" .. a}
},
}
m["cy"] = {
"Welsh",
9309,
"cel-bry",
Latn,
ancestors = {"wlm"},
sort_key = {
remove_diacritics = GRAVE .. ACUTE .. CIRC .. DIAER .. "'",
from = {"ch", "dd", "ff", "ng", "ll", "ph", "rh", "th"},
to = {"c" .. a, "d" .. a, "f" .. a, "g" .. a, "l" .. a, "p" .. a, "r" .. a, "t" .. a}
},
standardChars = "A-IL-PR-UWYa-il-pr-uwy0-9ÂâÊêÎîÔôÛûŴŵŶŷ" .. PUNCTUATION,
}
m["da"] = {
"Danish",
9035,
"gmq",
Latn,
ancestors = {"gmq-oda"},
sort_key = {
from = {"æ", "ø", "å"},
to = {"z" .. a, "z" .. b, "z" .. c}
},
}
m["de"] = {
"German",
188,
"gmw",
{"Latn", "Latf"},
ancestors = {"gmh"},
sort_key = {
remove_diacritics = GRAVE .. ACUTE .. CIRC .. DIAER .. RINGABOVE,
from = {"ß"},
to = {"ss"}
},
standardChars = "A-Za-z0-9ÄäÖöÜüß" .. PUNCTUATION,
}
m["dv"] = {
"Dhivehi",
32656,
"inc-ins",
{"Thaa", "Diak"},
ancestors = {"elu-prk"},
translit_module = "translit-redirect",
override_translit = true,
}
m["dz"] = {
"Dzongkha",
33081,
"sit-tib",
Tibt,
ancestors = {"xct"},
translit_module = "Tibt-translit",
override_translit = true,
display_text = "Tibt-displaytext",
entry_name = "Tibt-entryname",
sort_key = "Tibt-sortkey",
}
m["ee"] = {
"Ewe",
30005,
"alv-gbe",
Latn,
sort_key = {
remove_diacritics = TILDE,
from = {"ɖ", "dz", "ɛ", "ƒ", "gb", "ɣ", "kp", "ny", "ŋ", "ɔ", "ts", "ʋ"},
to = {"d" .. a, "d" .. b, "e" .. a, "f" .. a, "g" .. a, "g" .. b, "k" .. a, "n" .. a, "n" .. b, "o" .. a, "t" .. a, "v" .. a}
},
}
m["el"] = {
"Greek",
9129,
"grk",
{"Grek", "Brai"},
ancestors = {"grc"},
translit_module = "el-translit",
override_translit = true,
entry_name = {remove_diacritics = CARON .. DIAERBELOW .. BREVEBELOW},
sort_key = {Grek = "Grek-sortkey"},
standardChars = "ͺ;΄-ώϜϝ" .. PUNCTUATION,
}
m["en"] = {
"English",
1860,
"gmw",
{"Latn", "Brai", "Shaw", "Dsrt"}, -- entries in Shaw or Dsrt might require prior discussion
ancestors = {"enm"},
sort_key = {
Latn = {
remove_diacritics = GRAVE .. ACUTE .. CIRC .. TILDE .. MACRON .. DIAER .. RINGABOVE .. CARON .. CEDILLA .. "'",
from = {"æ", "œ"},
to = {"ae", "oe"}
},
},
wikimedia_codes = {"en", "simple"},
standardChars = "A-Za-z0-9" .. PUNCTUATION .. u(0x2800) .. "-" .. u(0x28FF),
}
m["eo"] = {
"Esperanto",
143,
"art",
Latn,
sort_key = {
remove_diacritics = GRAVE .. ACUTE,
from = {"ĉ", "ĝ", "ĥ", "ĵ", "ŝ", "ŭ"},
to = {"c" .. a, "g" .. a, "h" .. a, "j" .. a, "s" .. a, "u" .. a}
},
standardChars = "A-PRSTUVZa-prstuvzĉĈĝĜĵĴŝŜŭŬ0-9" .. PUNCTUATION,
}
m["es"] = {
"Spanish",
1321,
"roa-ibe",
LatnBrai,
ancestors = {"osp"},
sort_key = {
Latn = {
remove_diacritics = ACUTE .. DIAER .. CEDILLA,
from = {"ñ"},
to = {"n" .. a}
},
},
standardChars = "A-VXYZa-vxyz0-9ÁáÉéÍíÓóÚúÑñ¿¡" .. PUNCTUATION,
}
m["et"] = {
"Estonian",
9072,
"urj-fin",
Latn,
sort_key = {
from = {
"š", "ž", "õ", "ä", "ö", "ü", -- 2 chars
"z" -- 1 char
},
to = {
"s" .. a, "s" .. c, "w" .. a, "w" .. b, "w" .. c, "w" .. d,
"s" .. b
}
},
}
m["eu"] = {
"Basque",
8752,
"euq",
Latn,
sort_key = {
from = {"ç", "ñ"},
to = {"c" .. a, "n" .. a}
},
}
m["fa"] = {
"Persian",
9168,
"ira-swi",
{"fa-Arab"},
ancestors = {"pal"}, -- "ira-mid"
entry_name = {remove_diacritics = FATHATAN .. DAMMATAN .. KASRATAN .. KASHIDA .. FATHA .. DAMMA .. KASRA .. SHADDA .. SUKUN},
}
m["ff"] = {
"Fula",
33454,
"alv-fwo",
{"Latn", "Adlm"},
}
m["fi"] = {
"Finnish",
1412,
"urj-fin",
Latn,
entry_name = {remove_diacritics = "ˣ"}, -- used to indicate gemination of the next consonant
sort_key = {
remove_diacritics = GRAVE .. ACUTE .. CIRC .. TILDE .. DACUTE .. CARON .. CEDILLA .. "':",
from = {"ø", "æ", "œ", "ß"},
to = {"o", "ae", "oe", "ss"}
},
}
m["fj"] = {
"Fijian",
33295,
"poz-occ",
Latn,
}
m["fo"] = {
"Faroese",
25258,
"gmq",
Latn,
ancestors = {"non"},
sort_key = {
from = {"á", "ð", "í", "ó", "ú", "ý", "æ", "ø"},
to = {"a" .. a, "d" .. a, "i" .. a, "o" .. a, "u" .. a, "y" .. a, "z" .. a, "z" .. b}
},
}
m["fr"] = {
"French",
150,
"roa-oil",
LatnBrai,
ancestors = {"frm"},
sort_key = {Latn = "roa-oil-sortkey"},
standardChars = "A-Za-z0-9ÀÂÇÉÈÊËÎÏÔŒÛÙÜàâçéèêëîïôœûùü«»" .. PUNCTUATION,
}
m["fy"] = {
"West Frisian",
27175,
"gmw-fri",
Latn,
ancestors = {"ofs"},
sort_key = {
remove_diacritics = GRAVE .. ACUTE .. CIRC .. DIAER,
from = {"y"},
to = {"i"}
},
standardChars = "A-PR-WYZa-pr-wyz0-9Ææâäàéêëèïìôöòúûüùỳ" .. PUNCTUATION,
}
m["ga"] = {
"Irish",
9142,
"cel-gae",
LatnLatg,
ancestors = {"mga"},
sort_key = {
remove_diacritics = ACUTE,
from = {"ḃ", "ċ", "ḋ", "ḟ", "ġ", "ṁ", "ṗ", "ṡ", "ṫ"},
to = {"bh", "ch", "dh", "fh", "gh", "mh", "ph", "sh", "th"}
},
standardChars = "A-IL-PR-Ua-il-pr-u0-9ÁáÉéÍíÓóÚú" .. PUNCTUATION,
}
m["gd"] = {
"Scottish Gaelic",
9314,
"cel-gae",
LatnLatg,
ancestors = {"mga"},
sort_key = {remove_diacritics = GRAVE .. ACUTE},
standardChars = "A-IL-PR-Ua-il-pr-u0-9ÀàÈèÌìÒòÙù" .. PUNCTUATION,
}
m["gl"] = {
"Galician",
9307,
"roa-ibe",
Latn,
ancestors = {"roa-opt"},
sort_key = {
remove_diacritics = ACUTE,
from = {"ñ"},
to = {"n" .. a}
},
}
m["gn"] = {
"Guaraní",
35876,
"tup-gua",
Latn,
}
m["gu"] = {
"Gujarati",
5137,
"inc-wes",
{"Gujr"},
ancestors = {"inc-mgu"},
translit_module = "gu-translit",
}
m["gv"] = {
"Manx",
12175,
"cel-gae",
Latn,
ancestors = {"mga"},
sort_key = {remove_diacritics = CEDILLA .. "-"},
standardChars = "A-WYÇa-wyç0-9" .. PUNCTUATION,
}
m["ha"] = {
"Hausa",
56475,
"cdc-wst",
LatnArab,
entry_name = {Latn = {remove_diacritics = GRAVE .. ACUTE .. CIRC .. TILDE .. MACRON}},
sort_key = {
Latn = {
from = {"ɓ", "b'", "ɗ", "d'", "ƙ", "k'", "sh", "ƴ", "'y"},
to = {"b" .. a, "b" .. b, "d" .. a, "d" .. b, "k" .. a, "k" .. b, "s" .. a, "y" .. a, "y" .. b}
},
},
}
m["he"] = {
"Hebrew",
9288,
"sem-can",
{"Hebr", "Phnx", "Brai"},
entry_name = {Hebr = {remove_diacritics = u(0x0591) .. "-" .. u(0x05BD) .. u(0x05BF) .. "-" .. u(0x05C5) .. u(0x05C7) .. CGJ}},
}
m["hi"] = {
"Hindi",
1568,
"inc-hnd",
{"Deva", "Kthi", "Newa"},
ancestors = {"inc-ohi"},
translit_module = "hi-translit",
standardChars = "ँंअ-ऊएऐओ-घच-झट-नप-रलवशसहा-ूेैो-◌्।-॰ड़ढ़" .. PUNCTUATION,
}
m["ho"] = {
"Hiri Motu",
33617,
"crp",
Latn,
ancestors = {"meu"},
}
m["ht"] = {
"Haitian Creole",
33491,
"crp",
Latn,
ancestors = {"fr"},
sort_key = {
from = {
"oun", -- 3 chars
"an", "ch", "è", "en", "ng", "ò", "on", "ou", "ui" -- 2 chars
},
to = {
"o" .. d,
"a" .. a, "c" .. a, "e" .. a, "e" .. b, "n" .. a, "o" .. a, "o" .. b, "o" .. c, "u" .. a
}
},
}
m["hu"] = {
"Hungarian",
9067,
"urj-ugr",
{"Latn", "Hung"},
ancestors = {"ohu"},
sort_key = {
Latn = {
from = {
"dzs", -- 3 chars
"á", "cs", "dz", "é", "gy", "í", "ly", "ny", "ó", "ö", "ő", "sz", "ty", "ú", "ü", "ű", "zs", -- 2 chars
},
to = {
"d" .. b,
"a" .. a, "c" .. a, "d" .. a, "e" .. a, "g" .. a, "i" .. a, "l" .. a, "n" .. a, "o" .. a, "o" .. b, "o" .. c, "s" .. a, "t" .. a, "u" .. a, "u" .. b, "u" .. c, "z" .. a,
}
},
},
}
m["hy"] = {
"Armenian",
8785,
"hyx",
{"Armn", "Brai"},
ancestors = {"axm"},
translit_module = "Armn-translit",
override_translit = true,
entry_name = {
Armn = {
remove_diacritics = "՛՜՞՟",
from = {"եւ", "<sup>յ</sup>", "<sup>ի</sup>", "<sup>է</sup>"},
to = {"և", "յ", "ի", "է"}
},
},
sort_key = {
Armn = {
from = {
"ու", "եւ", -- 2 chars
"և" -- 1 char
},
to = {
"ւ", "եվ",
"եվ"
}
},
},
}
m["hz"] = {
"Herero",
33315,
"bnt-swb",
Latn,
}
m["ia"] = {
"Interlingua",
35934,
"art",
Latn,
}
m["id"] = {
"Indonesian",
9240,
"poz-mly",
Latn,
ancestors = {"ms"},
}
m["ie"] = {
"Interlingue",
35850,
"art",
Latn,
type = "appendix-constructed",
entry_name = {remove_diacritics = GRAVE .. ACUTE .. CIRC},
}
m["ig"] = {
"Igbo",
33578,
"alv-igb",
Latn,
entry_name = {remove_diacritics = GRAVE .. ACUTE .. MACRON},
sort_key = {
from = {"gb", "gh", "gw", "ị", "kp", "kw", "ṅ", "nw", "ny", "ọ", "sh", "ụ"},
to = {"g" .. a, "g" .. b, "g" .. c, "i" .. a, "k" .. a, "k" .. b, "n" .. a, "n" .. b, "n" .. c, "o" .. a, "s" .. a, "u" .. a}
},
}
m["ii"] = {
"Sichuan Yi",
34235,
"tbq-lol",
{"Yiii"},
translit_module = "ii-translit",
}
m["ik"] = {
"Inupiaq",
27183,
"esx-inu",
Latn,
sort_key = {
from = {
"ch", "ġ", "dj", "ḷ", "ł̣", "ñ", "ng", "r̂", "sr", "zr", -- 2 chars
"ł", "ŋ", "ʼ" -- 1 char
},
to = {
"c" .. a, "g" .. a, "h" .. a, "l" .. a, "l" .. c, "n" .. a, "n" .. b, "r" .. a, "s" .. a, "z" .. a,
"l" .. b, "n" .. b, "z" .. b
}
},
}
m["io"] = {
"Ido",
35224,
"art",
Latn,
}
m["is"] = {
"Icelandic",
294,
"gmq",
Latn,
ancestors = {"non"},
sort_key = {
from = {"á", "ð", "é", "í", "ó", "ú", "ý", "þ", "æ", "ö"},
to = {"a" .. a, "d" .. a, "e" .. a, "i" .. a, "o" .. a, "u" .. a, "y" .. a, "z" .. a, "z" .. b, "z" .. c}
},
}
m["it"] = {
"Italian",
652,
"roa-itd",
Latn,
sort_key = {remove_diacritics = GRAVE .. ACUTE .. CIRC .. DIAER .. RINGABOVE},
standardChars = "A-IL-VZa-il-vz0-9ÀàÈèÌìÒòÙùÉé" .. PUNCTUATION,
}
m["iu"] = {
"Inuktitut",
29921,
"esx-inu",
CansLatn,
translit_module = "translit-redirect",
override_translit = true,
}
m["ja"] = {
"Japanese",
5287,
"jpx",
{"Jpan", "Brai"},
ancestors = {"ojp"},
--[=[
-- Handled by jsort function in [[Module:ja]].
sort_key = {
from = {"[ぁァア]", "[ぃィイ]", "[ぅゔゥウヴ]", "[ぇェエ]", "[ぉォオ]", "[がゕカガヵ]", "[ぎキギ]", "[ぐクグㇰ]", "[げゖケゲヶ]", "[ごコゴ]", "[ざサザ]", "[じシジㇱ]", "[ずスズㇲ]", "[ぜセゼ]", "[ぞソゾ]", "[だタダ]", "[ぢチヂ]", "[っづッツヅ]", "[でテデ]", "[どトドㇳ]", "ナ", "ニ", "[ヌㇴ]", "ネ", "ノ", "[ばぱハバパㇵ]", "[びぴヒビピㇶ]", "[ぶぷフブプㇷ]", "[べぺヘベペㇸ]", "[ぼぽホボポㇹ]", "マ", "ミ", "[ムㇺ]", "メ", "モ", "[ゃャヤ]", "[ゅュユ]", "[ょョヨ]", "[ラㇻ]", "[リㇼ]", "[ルㇽ]", "[レㇾ]", "[ロㇿ]", "[ゎヮワヷ]", "[ヰヸ]", "[ヱヹ]", "[ヲヺ]", "ン", "[゙゚゛゜ゝゞ・ヽヾ]", "𛀀"},
to = {"あ", "い", "う", "え", "お", "か", "き", "く", "け", "こ", "さ", "し", "す", "せ", "そ", "た", "ち", "つ", "て", "と", "な", "に", "ぬ", "ね", "の", "は", "ひ", "ふ", "へ", "ほ", "ま", "み", "む", "め", "も", "や", "ゆ", "よ", "ら", "り", "る", "れ", "ろ", "わ", "ゐ", "ゑ", "を", "ん", "", "え"}
},
--]=]
}
m["jv"] = {
"Javanese",
33549,
"poz-sus",
{"Latn", "Java"},
translit_module = "jv-translit",
ancestors = {"kaw"},
link_tr = true,
sort_key = {
Latn = {
from = {"dh", "é", "è", "ng", "ny", "th"},
to = {"d" .. a, "e" .. a, "e" .. b, "n" .. a, "n" .. b, "t" .. a}
},
},
}
m["ka"] = {
"Georgian",
8108,
"ccs-gzn",
{"Geor", "Geok", "Hebr"}, -- Hebr is used to write Judeo-Georgian
ancestors = {"oge"},
translit_module = "Geor-translit",
override_translit = true,
entry_name = {remove_diacritics = CIRC},
}
m["kg"] = {
"Kongo",
33702,
"bnt-kng",
Latn,
}
m["ki"] = {
"Kikuyu",
33587,
"bnt-kka",
Latn,
}
m["kj"] = {
"Kwanyama",
1405077,
"bnt-ova",
Latn,
}
m["kk"] = {
"Kazakh",
9252,
"trk-kno",
{"Cyrl", "Latn", "kk-Arab"},
translit_module = "kk-translit",
override_translit = true,
sort_key = {
Cyrl = {
from = {"ә", "ғ", "ё", "қ", "ң", "ө", "ұ", "ү", "һ", "і"},
to = {"а" .. a, "г" .. a, "е" .. a, "к" .. a, "н" .. a, "о" .. a, "у" .. a, "у" .. b, "х" .. a, "ы" .. a}
},
},
}
m["kl"] = {
"Greenlandic",
25355,
"esx-inu",
Latn,
sort_key = {
from = {"æ", "ø", "å"},
to = {"z" .. a, "z" .. b, "z" .. c}
}
}
m["km"] = {
"Khmer",
9205,
"mkh-kmr",
{"Khmr"},
ancestors = {"xhm"},
translit_module = "km-translit",
}
m["kn"] = {
"Kannada",
33673,
"dra",
{"Knda"},
ancestors = {"dra-mkn"},
translit_module = "kn-translit",
}
m["ko"] = {
"Korean",
9176,
"qfa-kor",
{"Kore", "Brai"},
ancestors = {"ko-ear"},
translit_module = "ko-translit",
entry_name = {Kore = "Kore-entryname"},
}
m["kr"] = {
"Kanuri",
36094,
"ssa-sah",
LatnArab,
entry_name = {Latn = {remove_diacritics = GRAVE .. ACUTE .. CIRC .. BREVE}}, -- the sortkey and entry_name are only for standard Kanuri; when dialectal entries get added, someone will have to work out how the dialects should be represented orthographically
sort_key = {
Latn = {
from = {"ǝ", "ny", "ɍ", "sh"},
to = {"e" .. a, "n" .. a, "r" .. a, "s" .. a}
},
},
}
m["ks"] = {
"Kashmiri",
33552,
"inc-dar",
{"ks-Arab", "Deva", "Shrd", "Latn"},
translit_module = "translit-redirect",
}
-- "kv" IS TREATED AS "koi", "kpv", SEE WT:LT
m["kw"] = {
"Cornish",
25289,
"cel-bry",
Latn,
ancestors = {"cnx"},
sort_key = {
from = {"ch"},
to = {"c" .. a}
},
}
m["ky"] = {
"Kyrgyz",
9255,
"trk-kip",
CyrlLatnArab,
translit_module = "ky-translit",
override_translit = true,
sort_key = {
Cyrl = {
from = {"ё", "ң", "ө", "ү"},
to = {"е" .. a, "н" .. a, "о" .. a, "у" .. a}
},
},
}
m["la"] = {
"Latin",
397,
"itc",
{"Latn", "Ital"},
entry_name = {Latn = {remove_diacritics = MACRON .. BREVE .. DIAER .. DOUBLEINVBREVE}},
sort_key = {
Latn = {
from = {"æ", "œ"},
to = {"ae", "oe"}
},
},
standardChars = "A-Za-z0-9Æ挜Ā-ăĒ-ĕĪ-ĭŌ-ŏŪ-ŭȲȳ" .. MACRON .. BREVE .. PUNCTUATION,
}
m["lb"] = {
"Luxembourgish",
9051,
"gmw",
Latn,
ancestors = {"gmw-cfr"},
sort_key = {
from = {"ä", "ë", "é"},
to = {"z" .. a, "z" .. b, "z" .. c}
},
}
m["lg"] = {
"Luganda",
33368,
"bnt-nyg",
Latn,
entry_name = {remove_diacritics = ACUTE .. CIRC},
sort_key = {
from = {"ŋ"},
to = {"n" .. a}
},
}
m["li"] = {
"Limburgish",
102172,
"gmw",
Latn,
ancestors = {"dum"},
}
m["ln"] = {
"Lingala",
36217,
"bnt-bmo",
Latn,
sort_key = {
remove_diacritics = ACUTE .. CIRC .. CARON,
from = {"ɛ", "gb", "mb", "mp", "nd", "ng", "nk", "ns", "nt", "ny", "nz", "ɔ"},
to = {"e" .. a, "g" .. a, "m" .. a, "m" .. b, "n" .. a, "n" .. b, "n" .. c, "n" .. d, "n" .. e, "n" .. f, "n" .. g, "o" .. a}
},
}
m["lo"] = {
"Lao",
9211,
"tai-swe",
{"Laoo"},
translit_module = "lo-translit",
sort_key = "Laoo-sortkey",
standardChars = "0-9ກຂຄງຈຊຍດຕຖທນບປຜຝພຟມຢຣລວສຫອຮຯ-ໝ" .. PUNCTUATION,
}
m["lt"] = {
"Lithuanian",
9083,
"bat",
Latn,
ancestors = {"olt"},
entry_name = {remove_diacritics = GRAVE .. ACUTE .. TILDE},
sort_key = {
from = {"ą", "č", "ę", "ė", "į", "y", "š", "ų", "ū", "ž"},
to = {"a" .. a, "c" .. a, "e" .. a, "e" .. b, "i" .. a, "i" .. b, "s" .. a, "u" .. a, "u" .. b, "z" .. a}
},
}
m["lu"] = {
"Luba-Katanga",
36157,
"bnt-lub",
Latn,
}
m["lv"] = {
"Latvian",
9078,
"bat",
Latn,
entry_name = {
-- This attempts to convert vowels with tone marks to vowels either with
-- or without macrons. Specifically, there should be no macrons if the
-- vowel is part of a diphthong (including resonant diphthongs such
-- pìrksts -> pirksts not #pīrksts). What we do is first convert the
-- vowel + tone mark to a vowel + tilde in a decomposed fashion,
-- then remove the tilde in diphthongs, then convert the remaining
-- vowel + tilde sequences to macroned vowels, then delete any other
-- tilde. We leave already-macroned vowels alone: Both e.g. ar and ār
-- occur before consonants. FIXME: This still might not be sufficient.
from = {"([Ee])" .. CEDILLA, "[" .. GRAVE .. CIRC .. TILDE .."]", "([aAeEiIoOuU])" .. TILDE .."?([lrnmuiLRNMUI])" .. TILDE .. "?([^aAeEiIoOuU])", "([aAeEiIoOuU])" .. TILDE .."?([lrnmuiLRNMUI])" .. TILDE .."?$", "([iI])" .. TILDE .. "?([eE])" .. TILDE .. "?", "([aAeEiIuU])" .. TILDE, TILDE},
to = {"%1", TILDE, "%1%2%3", "%1%2", "%1%2", "%1" .. MACRON}
},
sort_key = {
from = {"ā", "č", "ē", "ģ", "ī", "ķ", "ļ", "ņ", "š", "ū", "ž"},
to = {"a" .. a, "c" .. a, "e" .. a, "g" .. a, "i" .. a, "k" .. a, "l" .. a, "n" .. a, "s" .. a, "u" .. a, "z" .. a}
},
}
m["mg"] = {
"Malagasy",
7930,
"poz-bre",
Latn,
}
m["mh"] = {
"Marshallese",
36280,
"poz-mic",
Latn,
sort_key = {
from = {"ā", "ļ", "m̧", "ņ", "n̄", "o̧", "ō", "ū"},
to = {"a" .. a, "l" .. a, "m" .. a, "n" .. a, "n" .. b, "o" .. a, "o" .. b, "u" .. a}
},
}
m["mi"] = {
"Maori",
36451,
"poz-pep",
Latn,
sort_key = {
remove_diacritics = MACRON,
from = {"ng", "wh"},
to = {"z" .. a, "z" .. b}
},
}
m["mk"] = {
"Macedonian",
9296,
"zls",
Cyrl,
translit_module = "mk-translit",
entry_name = {
remove_diacritics = ACUTE,
remove_exceptions = {"Ѓ", "ѓ", "Ќ", "ќ"}
},
sort_key = {
remove_diacritics = GRAVE,
from = {"ѓ", "ѕ", "ј", "љ", "њ", "ќ", "џ"},
to = {"д" .. a, "з" .. a, "и" .. a, "л" .. a, "н" .. a, "т" .. a, "ч" .. a}
},
}
m["ml"] = {
"Malayalam",
36236,
"dra",
{"Mlym"},
translit_module = "ml-translit",
override_translit = true,
}
m["mn"] = {
"Mongolian",
9246,
"xgn",
{"Cyrl", "Mong", "Latn"},
ancestors = {"cmg"},
translit_module = "translit-redirect",
override_translit = true,
display_text = {Mong = "Mong-displaytext"},
entry_name = {
Cyrl = {remove_diacritics = GRAVE .. ACUTE},
Mong = "Mong-entryname",
},
sort_key = {
Cyrl = {
remove_diacritics = GRAVE,
from = {"ё", "ө", "ү"},
to = {"е" .. a, "о" .. a, "у" .. a}
},
},
standardChars = "A-PR-UX-Za-pr-ux-zÇÖÜçöüŞşƟƵƶɵЁА-ШЫ-шы-яёҮүӨө—᠊-᠙ᠠ-ᡂ" .. PUNCTUATION,
}
-- "mo" IS TREATED AS "ro", SEE WT:LT
m["mr"] = {
"Marathi",
1571,
"inc-sou",
{"Deva", "Modi"},
ancestors = {"omr"},
translit_module = "translit-redirect",
entry_name = {
Deva = {
from = {"च़", "ज़", "झ़"},
to = {"च", "ज", "झ"}
},
},
}
m["ms"] = {
"Malay",
9237,
"poz-mly",
{"Latn", "ms-Arab"},
}
m["mt"] = {
"Maltese",
9166,
"sem-arb",
Latn,
ancestors = {"sqr"},
sort_key = {
from = {
"ċ", "ġ", "ż", -- Convert into PUA so that decomposed form does not get caught by the next step.
"([cgz])", -- Ensure "c" comes after "ċ", "g" comes after "ġ" and "z" comes after "ż".
"g" .. a .. "ħ", -- After initial conversion of "g".
c, d, "ħ", "ie", e -- Convert into final output.
},
to = {
c, d, e,
"%1" .. a,
"g" .. b,
"c", "g", "h" .. a, "i" .. a, "z"
}
},
}
m["my"] = {
"Burmese",
9228,
"tbq-brm",
{"Mymr"},
ancestors = {"obr"},
translit_module = "my-translit",
override_translit = true,
sort_key = {
from = {"ျ", "ြ", "ွ", "ှ", "ဿ"},
to = {"္ယ", "္ရ", "္ဝ", "္ဟ", "သ္သ"}
},
}
m["na"] = {
"Nauruan",
13307,
"poz-mic",
Latn,
}
m["nb"] = {
"Norwegian Bokmål",
25167,
"gmq",
Latn,
ancestors = {"gmq-mno"},
sort_key = "no-sortkey",
wikimedia_codes = {"no"},
}
m["nd"] = {
"Northern Ndebele",
35613,
"bnt-ngu",
Latn,
entry_name = {remove_diacritics = GRAVE .. ACUTE .. CIRC .. MACRON .. CARON},
}
m["ne"] = {
"Nepali",
33823,
"inc-pah",
{"Deva", "Newa"},
translit_module = "ne-translit",
}
m["ng"] = {
"Ndonga",
33900,
"bnt-ova",
Latn,
}
m["nl"] = {
"Dutch",
7411,
"gmw",
Latn,
ancestors = {"dum"},
sort_key = {remove_diacritics = GRAVE .. ACUTE .. CIRC .. TILDE .. DIAER .. RINGABOVE .. CEDILLA .. "'"},
standardChars = "A-Za-z0-9" .. PUNCTUATION .. u(0x2800) .. "-" .. u(0x28FF),
}
m["nn"] = {
"Norwegian Nynorsk",
25164,
"gmq",
Latn,
ancestors = {"gmq-mno"},
sort_key = "no-sortkey",
}
m["no"] = {
"Norwegian",
9043,
"gmq",
Latn,
ancestors = {"gmq-mno"},
sort_key = "no-sortkey",
}
m["nr"] = {
"Southern Ndebele",
36785,
"bnt-ngu",
Latn,
entry_name = {remove_diacritics = GRAVE .. ACUTE .. CIRC .. MACRON .. CARON},
}
m["nv"] = {
"Navajo",
13310,
"apa",
Latn,
sort_key = {
remove_diacritics = ACUTE .. OGONEK,
from = {
"chʼ", "tłʼ", "tsʼ", -- 3 chars
"ch", "dl", "dz", "gh", "hw", "kʼ", "kw", "sh", "tł", "ts", "zh", -- 2 chars
"ł", "ʼ" -- 1 char
},
to = {
"c" .. b, "t" .. b, "t" .. d,
"c" .. a, "d" .. a, "d" .. b, "g" .. a, "h" .. a, "k" .. a, "k" .. b, "s" .. a, "t" .. a, "t" .. c, "z" .. a,
"l" .. a, "z" .. b
}
},
}
m["ny"] = {
"Chichewa",
33273,
"bnt-nys",
Latn,
entry_name = {remove_diacritics = ACUTE .. CIRC},
sort_key = {
from = {"ng'"},
to = {"ng"}
},
}
m["oc"] = {
"Occitan",
14185,
"roa-ocr",
{"Latn", "Hebr"},
ancestors = {"pro"},
sort_key = {
Latn = {
remove_diacritics = GRAVE .. ACUTE .. DIAER .. CEDILLA,
from = {"([lns])·h"},
to = {"%1h"}
},
},
}
m["oj"] = {
"Ojibwe",
33875,
"alg",
CansLatn,
sort_key = {
Latn = {
from = {"aa", "ʼ", "ii", "oo", "sh", "zh"},
to = {"a" .. a, "h" .. a, "i" .. a, "o" .. a, "s" .. a, "z" .. a}
},
},
}
m["om"] = {
"Oromo",
33864,
"cus-eas",
{"Latn", "Ethi"},
}
m["or"] = {
"Oriya",
33810,
"inc-eas",
{"Orya"},
ancestors = {"inc-mor"},
translit_module = "or-translit",
}
m["os"] = {
"Ossetian",
33968,
"xsc",
CyrlGeorLatn,
ancestors = {"oos"},
translit_module = "os-translit",
override_translit = true,
entry_name = {remove_diacritics = GRAVE .. ACUTE},
sort_key = {
Cyrl = {
from = {"ӕ", "гъ", "дж", "дз", "ё", "къ", "пъ", "тъ", "хъ", "цъ", "чъ"},
to = {"а" .. a, "г" .. a, "д" .. a, "д" .. b, "е" .. a, "к" .. a, "п" .. a, "т" .. a, "х" .. a, "ц" .. a, "ч" .. a}
},
},
}
m["pa"] = {
"Punjabi",
58635,
"inc-pan",
{"Guru", "pa-Arab"},
ancestors = {"inc-opa"},
translit_module = "translit-redirect",
entry_name = {
remove_diacritics = FATHATAN .. DAMMATAN .. KASRATAN .. FATHA .. DAMMA .. KASRA .. SHADDA .. SUKUN .. NUNGHUNNA,
from = {u(0x0768), u(0x08C7)},
to = {"ن", "ل"}
},
}
m["pi"] = {
"Pali",
36727,
"inc-mid",
{"Latn", "Brah", "Deva", "Beng", "Sinh", "Mymr", "Thai", "Lana", "Laoo", "Khmr"},
ancestors = {"sa"},
translit_module = "translit-redirect",
entry_name = {
from = {"ึ", u(0xF700), u(0xF70F), u(0xFE00)},
to = {"ิํ", "ฐ", "ญ"}
},
sort_key = {
from = {"ā", "ī", "ū", "ḍ", "ḷ", "m[" .. DOTABOVE .. DOTBELOW .. "]", "ṅ", "ñ", "ṇ", "ṭ", "([เโ])([ก-ฮ])", "([ເໂ])([ກ-ຮ])", "ᩔ", "ᩕ", "ᩖ", "ᩘ", "([ᨭ-ᨱ])ᩛ", "([ᨷ-ᨾ])ᩛ", "ᩤ", u(0xFE00), u(0x200D)},
to = {"a~", "i~", "u~", "d~", "l~", "m~", "n~", "n~~", "n~~~", "t~", "%2%1", "%2%1", "ᩈ᩠ᩈ", "᩠ᩁ", "᩠ᩃ", "ᨦ᩠", "%1᩠ᨮ", "%1᩠ᨻ", "ᩣ"}
},
}
m["pl"] = {
"Polish",
809,
"zlw-lch",
Latn,
ancestors = {"zlw-opl"},
sort_key = {
from = {"ą", "ć", "ę", "ł", "ń", "ó", "ś", "ź", "ż"},
to = {"a" .. a, "c" .. a, "e" .. a, "l" .. a, "n" .. a, "o" .. a, "s" .. a, "z" .. a, "z" .. b}
},
}
m["ps"] = {
"Pashto",
58680,
"ira-pat",
{"ps-Arab"},
}
m["pt"] = {
"Portuguese",
5146,
"roa-ibe",
LatnBrai,
ancestors = {"roa-opt"},
sort_key = {Latn = {remove_diacritics = GRAVE .. ACUTE .. CIRC .. TILDE .. DIAER .. CEDILLA}},
}
m["qu"] = {
"Quechua",
5218,
"qwe",
Latn,
}
m["rm"] = {
"Romansch",
13199,
"roa-rhe",
Latn,
}
m["ro"] = {
"Romanian",
7913,
"roa-eas",
{"Latn", "Cyrl"},
sort_key = {
Latn = {
from = {"ă", "â", "î", "ș", "ț"},
to = {"a" .. a, "a" .. b, "i" .. a, "s" .. a, "t" .. a}
},
Cyrl = {
from = {"ӂ"},
to = {"ж" .. a}
},
},
}
m["ru"] = {
"Russian",
7737,
"zle",
{"Cyrl", "Brai"},
translit_module = "ru-translit",
entry_name = {
Cyrl = {
remove_diacritics = GRAVE .. ACUTE .. DIAER,
remove_exceptions = {"Ё", "ё"}
},
},
sort_key = {
Cyrl = {
from = {"ё", "і", "ѣ", "ѳ", "ѵ"},
to = {"е" .. a, "и" .. a, "ь" .. a, "я" .. a, "я" .. b}
},
},
standardChars = "ЁА-яё0-9—" .. PUNCTUATION,
}
m["rw"] = {
"Rwanda-Rundi",
3217514,
"bnt-glb",
Latn,
entry_name = {remove_diacritics = ACUTE .. CIRC .. MACRON .. CARON},
}
m["sa"] = {
"Sanskrit",
11059,
"inc-old",
{"Deva", "Bali", "as-Beng", "Beng", "Bhks", "Brah", "Gran", "Gujr", "Guru", "Hani", "Java", "Kawi", "Khar", "Khmr", "Knda", "Lana", "Laoo", "Marc", "Mlym", "Modi", "Mong", "mnc-Mong", "xwo-Mong", "Mymr", "Nand", "Newa", "Orya", "Phag", "Ranj", "Saur", "Shrd", "Sidd", "Sinh", "Taml", "Tang", "Telu", "Thai", "Tibt", "Tirh"},
translit_module = "translit-redirect",
display_text = {
Mong = "Mong-displaytext",
Tibt = "Tibt-displaytext",
},
entry_name = {
from = {"ึ", u(0xF700), u(0xF70F), u(0xFE00)},
to = {"ิํ", "ฐ", "ญ"},
Mong = "Mong-entryname",
Tibt = "Tibt-entryname",
},
sort_key = {
from = {"ā", "ī", "ū", "ḍ", "ḷ", "ḹ", "m[" .. DOTABOVE .. DOTBELOW .. "]", "ṅ", "ñ", "ṇ", "ṛ", "ṝ", "ś", "ṣ", "ṭ", "([เโไ])([ก-ฮ])", "([ເໂໄ])([ກ-ຮ])", "ᩔ", "ᩕ", "ᩖ", "ᩘ", "([ᨭ-ᨱ])ᩛ", "([ᨷ-ᨾ])ᩛ", "ᩤ", u(0xFE00), u(0x200D)},
to = {"a~", "i~", "u~", "d~", "l~", "l~~", "m~", "n~", "n~~", "n~~~", "r~", "r~~", "s~", "s~~", "t~", "%2%1", "%2%1", "ᩈ᩠ᩈ", "᩠ᩁ", "᩠ᩃ", "ᨦ᩠", "%1᩠ᨮ", "%1᩠ᨻ", "ᩣ"}
},
}
m["sc"] = {
"Sardinian",
33976,
"roa",
Latn,
}
m["sd"] = {
"Sindhi",
33997,
"inc-snd",
{"sd-Arab", "Deva", "Sind", "Khoj"},
translit_module = "translit-redirect",
entry_name = {
remove_diacritics = KASHIDA .. FATHATAN .. DAMMATAN .. KASRATAN .. FATHA .. DAMMA .. KASRA .. SHADDA .. SUKUN .. SUPERALEF,
from = {u(0x0671)},
to = {u(0x0627)}
},
ancestors = {"inc-vra"},
}
m["se"] = {
"Northern Sami",
33947,
"smi",
Latn,
display_text = {
from = {"'"},
to = {"ˈ"}
},
entry_name = {remove_diacritics = MACRON .. DOTBELOW .. "'ˈ"},
sort_key = {
from = {"á", "č", "đ", "ŋ", "š", "ŧ", "ž"},
to = {"a" .. a, "c" .. a, "d" .. a, "n" .. a, "s" .. a, "t" .. a, "z" .. a}
},
standardChars = "A-PR-VZa-pr-vz0-9ÁáČčĐđŊŋŠšŦŧŽž" .. PUNCTUATION,
}
m["sg"] = {
"Sango",
33954,
"crp",
Latn,
ancestors = {"ngb"},
}
m["sh"] = {
"Serbo-Croatian",
9301,
"zls",
{"Latn", "Cyrl", "Glag"},
entry_name = {
Latn = {
remove_diacritics = GRAVE .. ACUTE .. TILDE .. MACRON .. DGRAVE .. INVBREVE,
remove_exceptions = {"Ć", "ć", "Ś", "ś", "Ź", "ź"}
},
Cyrl = {
remove_diacritics = GRAVE .. ACUTE .. TILDE .. MACRON .. DGRAVE .. INVBREVE,
remove_exceptions = {"З́", "з́", "С́", "с́"}
},
},
sort_key = {
Latn = {
from = {"č", "ć", "dž", "đ", "lj", "nj", "š", "ś", "ž", "ź"},
to = {"c" .. a, "c" .. b, "d" .. a, "d" .. b, "l" .. a, "n" .. a, "s" .. a, "s" .. b, "z" .. a, "z" .. b}
},
Cyrl = {
from = {"ђ", "з́", "ј", "љ", "њ", "с́", "ћ", "џ"},
to = {"д" .. a, "з" .. a, "и" .. a, "л" .. a, "н" .. a, "с" .. a, "т" .. a, "ч" .. a}
},
},
wikimedia_codes = {"sh", "bs", "hr", "sr"},
}
m["si"] = {
"Sinhalese",
13267,
"inc-ins",
{"Sinh"},
ancestors = {"elu-prk"},
translit_module = "si-translit",
override_translit = true,
}
m["sk"] = {
"Slovak",
9058,
"zlw",
Latn,
sort_key = {remove_diacritics = ACUTE .. CIRC .. DIAER},
}
m["sl"] = {
"Slovene",
9063,
"zls",
Latn,
entry_name = {
remove_diacritics = GRAVE .. ACUTE .. CIRC .. MACRON .. DGRAVE .. INVBREVE .. DOTBELOW,
from = {"Ə", "ə", "Ł", "ł"},
to = {"E", "e", "L", "l"}
},
sort_key = {
remove_diacritics = TILDE .. DOTABOVE .. DIAER .. RINGABOVE .. RINGBELOW .. OGONEK,
from = {"č", "š", "ž"},
to = {"c" .. a, "s" .. a, "z" .. a}
},
}
m["sm"] = {
"Samoan",
34011,
"poz-pnp",
Latn,
}
m["sn"] = {
"Shona",
34004,
"bnt-sho",
Latn,
entry_name = {remove_diacritics = ACUTE},
}
m["so"] = {
"Somali",
13275,
"cus-eas",
{"Latn", "Arab", "Osma"},
entry_name = {Latn = {remove_diacritics = GRAVE .. ACUTE .. CIRC}},
}
m["sq"] = {
"Albanian",
8748,
"sqj",
{"Latn", "Grek", "Elba"},
entry_name = {remove_diacritics = ACUTE},
sort_key = {remove_diacritics = CIRC .. TILDE .. DIAER .. CEDILLA},
}
m["ss"] = {
"Swazi",
34014,
"bnt-ngu",
Latn,
entry_name = {remove_diacritics = GRAVE .. ACUTE .. CIRC .. MACRON .. CARON},
}
m["st"] = {
"Sotho",
34340,
"bnt-sts",
Latn,
entry_name = {remove_diacritics = GRAVE .. ACUTE .. CIRC .. MACRON .. CARON},
}
m["su"] = {
"Sundanese",
34002,
"poz-msa",
{"Latn", "Sund"},
ancestors = {"osn"},
translit_module = "su-translit",
}
m["sv"] = {
"Swedish",
9027,
"gmq",
Latn,
ancestors = {"gmq-osw"},
}
m["sw"] = {
"Swahili",
7838,
"bnt-swh",
LatnArab,
sort_key = {
Latn = {
from = {"ng'"},
to = {"ng" .. a}
},
},
}
m["ta"] = {
"Tamil",
5885,
"dra",
{"Taml"},
ancestors = {"oty"},
translit_module = "ta-translit",
override_translit = true,
}
m["te"] = {
"Telugu",
8097,
"dra",
{"Telu"},
translit_module = "te-translit",
override_translit = true,
}
m["tg"] = {
"Tajik",
9260,
"ira-swi",
{"Cyrl", "fa-Arab", "Latn"},
ancestors = {"fa-cls"},
translit_module = "tg-translit",
override_translit = true,
entry_name = {remove_diacritics = GRAVE .. ACUTE},
sort_key = {
Cyrl = {
from = {"ғ", "ё", "ӣ", "қ", "ӯ", "ҳ", "ҷ"},
to = {"г" .. a, "е" .. a, "и" .. a, "к" .. a, "у" .. a, "х" .. a, "ч" .. a}
},
},
}
m["th"] = {
"Thai",
9217,
"tai-swe",
{"Thai", "Brai"},
translit_module = "th-translit",
sort_key = {Thai = "Thai-sortkey"},
}
m["ti"] = {
"Tigrinya",
34124,
"sem-eth",
Ethi,
translit_module = "Ethi-translit",
}
m["tk"] = {
"Turkmen",
9267,
"trk-ogz",
{"Latn", "Cyrl", "Arab"},
entry_name = {remove_diacritics = MACRON},
sort_key = {
Latn = {
from = {"ç", "ä", "ž", "ň", "ö", "ş", "ü", "ý"},
to = {"c" .. a, "e" .. a, "j" .. a, "n" .. a, "o" .. a, "s" .. a, "u" .. a, "y" .. a}
},
Cyrl = {
from = {"ё", "җ", "ң", "ө", "ү", "ә"},
to = {"е" .. a, "ж" .. a, "н" .. a, "о" .. a, "у" .. a, "э" .. a}
},
},
}
m["tl"] = {
"Tagalog",
34057,
"phi",
{"Latn", "Tglg"},
translit_module = "tl-translit",
override_translit = true,
entry_name = {Latn = {remove_diacritics = GRAVE .. ACUTE .. CIRC}},
}
m["tn"] = {
"Tswana",
34137,
"bnt-sts",
Latn,
}
m["to"] = {
"Tongan",
34094,
"poz-pol",
Latn,
entry_name = {remove_diacritics = ACUTE},
sort_key = {remove_diacritics = MACRON},
}
m["tr"] = {
"Turkish",
256,
"trk-ogz",
Latn,
ancestors = {"ota"},
dotted_dotless_i = true,
sort_key = {
from = {
"i", -- Ensure "i" comes after "ı".
"ç", "ğ", "ı", "ö", "ş", "ü"
},
to = {
"i" .. a,
"c" .. a, "g" .. a, "i", "o" .. a, "s" .. a, "u" .. a
}
},
}
m["ts"] = {
"Tsonga",
34327,
"bnt-tsr",
Latn,
}
m["tt"] = {
"Tatar",
25285,
"trk-kbu",
{"Cyrl", "Latn", "tt-Arab"},
translit_module = "tt-translit",
override_translit = true,
dotted_dotless_i = true,
sort_key = {
Cyrl = {
from = {"ә", "ў", "ғ", "ё", "җ", "қ", "ң", "ө", "ү", "һ"},
to = {"а" .. a, "в" .. a, "г" .. a, "е" .. a, "ж" .. a, "к" .. a, "н" .. a, "о" .. a, "у" .. a, "х" .. a}
},
Latn = {
from = {
"i", -- Ensure "i" comes after "ı".
"ä", "ə", "ç", "ğ", "ı", "ñ", "ŋ", "ö", "ɵ", "ş", "ü"
},
to = {
"i" .. a,
"a" .. a, "a" .. b, "c" .. a, "g" .. a, "i", "n" .. a, "n" .. b, "o" .. a, "o" .. b, "s" .. a, "u" .. a
}
},
},
}
-- "tw" IS TREATED AS "ak", SEE WT:LT
m["ty"] = {
"Tahitian",
34128,
"poz-pep",
Latn,
}
m["ug"] = {
"Uyghur",
13263,
"trk-kar",
{"ug-Arab", "Latn", "Cyrl"},
ancestors = {"chg"},
translit_module = "ug-translit",
override_translit = true,
}
m["uk"] = {
"Ukrainian",
8798,
"zle",
Cyrl,
ancestors = {"zle-ort"},
translit_module = "uk-translit",
entry_name = {remove_diacritics = GRAVE .. ACUTE},
sort_key = {
from = {
"ї", -- 2 chars
"ґ", "є", "і" -- 1 char
},
to = {
"и" .. b,
"г" .. a, "е" .. a, "и" .. a
}
},
standardChars = "ЄІЇА-ЩЬЮ-щьюяєії" .. PUNCTUATION,
}
m["ur"] = {
"Urdu",
1617,
"inc-hnd",
{"ur-Arab"},
ancestors = {"inc-ohi"},
entry_name = {remove_diacritics = KASHIDA .. FATHATAN .. DAMMATAN .. KASRATAN .. FATHA .. DAMMA .. KASRA .. SHADDA .. SUKUN .. NUNGHUNNA},
-- put Judeo-Urdu (Hebrew-script Urdu) under the category header
-- U+FB21 HEBREW LETTER WIDE ALEF so that it sorts after Arabic script titles
sort_key = {
from = {"^%f[" .. u(0x5D0) .. "-" .. u(0x5EA) .. "]"},
to = {u(0xFB21)},
},
}
m["uz"] = {
"Uzbek",
9264,
"trk-kar",
LatnCyrlfaArab,
ancestors = {"chg"},
translit_module = "uz-translit",
sort_key = {
Latn = {
from = {"oʻ", "gʻ", "sh", "ch", "ng"},
to = {"z" .. a, "z" .. b, "z" .. c, "z" .. d, "z" .. e}
},
Cyrl = {
from = {"ё", "ў", "қ", "ғ", "ҳ"},
to = {"е" .. a, "я" .. a, "я" .. b, "я" .. c, "я" .. d}
},
},
}
m["ve"] = {
"Venda",
32704,
"bnt-bso",
Latn,
}
m["vi"] = {
"Vietnamese",
9199,
"mkh-vie",
LatnHani,
ancestors = {"mkh-mvi"},
sort_key = {
Latn = "vi-sortkey",
Han = "zh-sortkey",
},
}
m["vo"] = {
"Volapük",
36986,
"art",
Latn,
}
m["wa"] = {
"Walloon",
34219,
"roa-oil",
Latn,
ancestors = {"fro"},
sort_key = "roa-oil-sortkey",
}
m["wo"] = {
"Wolof",
34257,
"alv-fwo",
LatnArab,
}
m["xh"] = {
"Xhosa",
13218,
"bnt-ngu",
Latn,
entry_name = {remove_diacritics = GRAVE .. ACUTE .. CIRC .. MACRON .. CARON},
}
m["yi"] = {
"Yiddish",
8641,
"gmw",
{"Hebr"},
ancestors = {"gmh"},
translit_module = "yi-translit",
sort_key = {
from = {"א[ַָ]", "בּ", "ו[ֹּ]", "יִ", "ײַ", "פֿ"},
to = {"א", "ב", "ו", "י", "יי", "פ"}
},
}
m["yo"] = {
"Yoruba",
34311,
"alv-yor",
LatnArab,
entry_name = {Latn = {remove_diacritics = GRAVE .. ACUTE .. MACRON}},
sort_key = {
Latn = {
from = {"ẹ", "gb", "ọ", "ṣ"},
to = {"e" .. a, "g" .. a, "o" .. a, "s" .. a}
},
},
}
m["za"] = {
"Zhuang",
13216,
"tai",
LatnHani,
sort_key = {
Latn = "za-sortkey",
Han = "zh-sortkey",
},
}
m["zh"] = {
"Chinese",
7850,
"zhx",
{"Hant", "Hans", "Hani", "Latn", "Bopo", "Brai", "Nshu"},
ancestors = {"ltc"},
sort_key = {Han = "zh-sortkey"},
}
m["zu"] = {
"Zulu",
10179,
"bnt-ngu",
Latn,
entry_name = {remove_diacritics = GRAVE .. ACUTE .. CIRC .. MACRON .. CARON},
}
return m